lightspeed-stack 0.4.0__tar.gz → 0.4.1__tar.gz

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lightspeed-stack
-Version: 0.4.0
+Version: 0.4.1
 Summary: LLM tooling stack
 Keywords: LLM,RAG
 Maintainer-Email: =?utf-8?b?UGF2ZWwgVGnFoW5vdnNrw70=?= <tisnik@centrum.cz>
@@ -218,8 +218,8 @@ Requires-Python: <3.14,>=3.12
 Requires-Dist: fastapi>=0.115.12
 Requires-Dist: uvicorn>=0.34.3
 Requires-Dist: kubernetes>=30.1.0
-Requires-Dist: llama-stack==0.3.5
-Requires-Dist: llama-stack-client==0.3.5
+Requires-Dist: llama-stack==0.4.3
+Requires-Dist: llama-stack-client==0.4.3
 Requires-Dist: rich>=14.0.0
 Requires-Dist: cachetools>=6.1.0
 Requires-Dist: prometheus-client>=0.22.1
@@ -241,6 +241,7 @@ Requires-Dist: PyYAML>=6.0.0
 Requires-Dist: einops>=0.8.1
 Requires-Dist: azure-core>=1.38.0
 Requires-Dist: azure-identity
+Requires-Dist: pyasn1>=0.6.2
 Description-Content-Type: text/markdown
 
 # lightspeed-stack
@@ -251,7 +252,7 @@ Description-Content-Type: text/markdown
 [![License](https://img.shields.io/badge/license-Apache-blue)](https://github.com/lightspeed-core/lightspeed-stack/blob/main/LICENSE)
 [![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
 [![Required Python version](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Flightspeed-core%2Flightspeed-stack%2Frefs%2Fheads%2Fmain%2Fpyproject.toml)](https://www.python.org/)
-[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.4.0)
+[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.4.1)
 
 Lightspeed Core Stack (LCS) is an AI-powered assistant that provides answers to product questions using backend LLM services, agents, and RAG databases.
 
@@ -281,6 +282,7 @@ The service includes comprehensive user data collection capabilities for various
         * [1. Static Tokens from Files (Recommended for Service Credentials)](#1-static-tokens-from-files-recommended-for-service-credentials)
         * [2. Kubernetes Service Account Tokens (For K8s Deployments)](#2-kubernetes-service-account-tokens-for-k8s-deployments)
         * [3. Client-Provided Tokens (For Per-User Authentication)](#3-client-provided-tokens-for-per-user-authentication)
+        * [Client-Authenticated MCP Servers Discovery](#client-authenticated-mcp-servers-discovery)
         * [Combining Authentication Methods](#combining-authentication-methods)
         * [Authentication Method Comparison](#authentication-method-comparison)
         * [Important: Automatic Server Skipping](#important-automatic-server-skipping)
@@ -635,7 +637,7 @@ mcp_servers:
       Authorization: "kubernetes"    # Uses user's k8s token from request auth
 ```
 
-The user's Kubernetes token is extracted from the incoming request's `Authorization` header and forwarded to the MCP server.
+**Note:** Kubernetes token-based MCP authorization only works when Lightspeed Core Stack is configured with Kubernetes authentication (`authentication.k8s`). For any other authentication types, MCP servers configured with `Authorization: "kubernetes"` are removed from the available MCP servers list.
 
 ##### 3. Client-Provided Tokens (For Per-User Authentication)
 
@@ -663,6 +665,34 @@ curl -X POST "http://localhost:8080/v1/query" \
 
 **Structure**: `MCP-HEADERS: {"<server-name>": {"<header-name>": "<header-value>", ...}, ...}`
 
+##### Client-Authenticated MCP Servers Discovery
+
+To help clients determine which MCP servers require client-provided tokens, use the **MCP Client Auth Options** endpoint:
+
+```bash
+GET /v1/mcp-auth/client-options
+```
+
+**Response:**
+```json
+{
+  "servers": [
+    {
+      "name": "user-specific-service",
+      "client_auth_headers": ["Authorization", "X-User-Token"]
+    },
+    {
+      "name": "github-integration",
+      "client_auth_headers": ["Authorization"]
+    }
+  ]
+}
+```
+
+This endpoint returns only MCP servers configured with `authorization_headers: "client"`, along with the specific header names that need to be provided via `MCP-HEADERS`. Servers using file-based or Kubernetes authentication are not included in this response.
+
+**Use case:** Clients can call this endpoint at startup or before making requests to discover which servers they can authenticate with using their own tokens.
+
 ##### Combining Authentication Methods
 
 You can mix and match authentication methods across different MCP servers, and even combine multiple methods for a single server:
@@ -943,6 +973,7 @@ options:
   -v, --verbose         make it verbose
   -d, --dump-configuration
                         dump actual configuration into JSON file and quit
+  -s, --dump-schema     dump configuration schema into OpenAPI-compatible file and quit
   -c CONFIG_FILE, --config CONFIG_FILE
                         path to configuration file (default: lightspeed-stack.yaml)
 
@@ -956,14 +987,19 @@ Usage: make <OPTIONS> ... <TARGETS>
 Available targets are:
 
 run                               Run the service locally
+help                              Show this help screen
+run-llama-stack                   Start Llama Stack with enriched config (for local service mode)
 test-unit                         Run the unit tests
 test-integration                  Run integration tests tests
 test-e2e                          Run end to end tests for the service
+test-e2e-local                    Run end to end tests for the service
+benchmarks                        Run benchmarks
 check-types                       Checks type hints in sources
 security-check                    Check the project for security issues
 format                            Format the code into unified format
 schema                            Generate OpenAPI schema file
 openapi-doc                       Generate OpenAPI documentation
+generate-documentation            Generate documentation
 requirements.txt                  Generate requirements.txt file containing hashes for all non-devel packages
 doc                               Generate documentation for developers
 docs/config.puml                  Generate PlantUML class diagram for configuration
@@ -978,7 +1014,8 @@ ruff                              Check source code using Ruff linter
 verify                            Run all linters
 distribution-archives             Generate distribution archives to be uploaded into Python registry
 upload-distribution-archives      Upload distribution archives into Python registry
-help                              Show this help screen
+konflux-requirements              generate hermetic requirements.*.txt file for konflux build
+konflux-rpm-lock 	                generate rpm.lock.yaml file for konflux build
 ```
 
 ## Running Linux container image
@@ -1440,7 +1477,10 @@ The script also updates the Tekton pipeline configurations (`.tekton/lightspeed-
 
 ### Updating RPM Dependencies
 
-**Prerequisites:** Install [rpm-lockfile-prototype](https://github.com/konflux-ci/rpm-lockfile-prototype?tab=readme-ov-file#installation)
+**Prerequisites:**
+- Install [rpm-lockfile-prototype](https://github.com/konflux-ci/rpm-lockfile-prototype?tab=readme-ov-file#installation)
+- Have an active RHEL Subscription, get activation keys from [RH console](https://console.redhat.com/insights/connector/activation-keys)
+- Have `dnf` installed in system
 
 **Steps:**
 
@@ -1448,12 +1488,24 @@ The script also updates the Tekton pipeline configurations (`.tekton/lightspeed-
 
 2. **If you changed the base image**, extract its repo file:
 ```shell
+# UBI images
 podman run -it $BASE_IMAGE cat /etc/yum.repos.d/ubi.repo > ubi.repo
+# RHEL images
+podman run -it $BASE_IMAGE cat /etc/yum.repos.d/redhat.repo > redhat.repo
+```
+If the repo file contains too many entries, we can filter them and keep only required repositories.
+Here is the command to check active repositories:
+```shell
+dnf repolist
+```
+Replace the architecture tag (`uname -m`) to `$basearch` so that rpm-lockfile-prototype can replace it with requested architecture names.
+```shell
+sed -i "s/$(uname -m)/\$basearch/g" redhat.repo
 ```
 
-3. **Generate the lock file**:
+1. **Generate the lock file**:
 ```shell
-rpm-lockfile-prototype --image $BASE_IMAGE rpms.in.yaml
+make konflux-rpm-lock
 ```
 
 This creates `rpms.lock.yaml` with pinned RPM versions.

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/README.md

@@ -6,7 +6,7 @@
 [![License](https://img.shields.io/badge/license-Apache-blue)](https://github.com/lightspeed-core/lightspeed-stack/blob/main/LICENSE)
 [![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
 [![Required Python version](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Flightspeed-core%2Flightspeed-stack%2Frefs%2Fheads%2Fmain%2Fpyproject.toml)](https://www.python.org/)
-[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.4.0)
+[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.4.1)
 
 Lightspeed Core Stack (LCS) is an AI-powered assistant that provides answers to product questions using backend LLM services, agents, and RAG databases.
 
@@ -36,6 +36,7 @@ The service includes comprehensive user data collection capabilities for various
         * [1. Static Tokens from Files (Recommended for Service Credentials)](#1-static-tokens-from-files-recommended-for-service-credentials)
         * [2. Kubernetes Service Account Tokens (For K8s Deployments)](#2-kubernetes-service-account-tokens-for-k8s-deployments)
         * [3. Client-Provided Tokens (For Per-User Authentication)](#3-client-provided-tokens-for-per-user-authentication)
+        * [Client-Authenticated MCP Servers Discovery](#client-authenticated-mcp-servers-discovery)
         * [Combining Authentication Methods](#combining-authentication-methods)
         * [Authentication Method Comparison](#authentication-method-comparison)
         * [Important: Automatic Server Skipping](#important-automatic-server-skipping)
@@ -390,7 +391,7 @@ mcp_servers:
       Authorization: "kubernetes"    # Uses user's k8s token from request auth
 ```
 
-The user's Kubernetes token is extracted from the incoming request's `Authorization` header and forwarded to the MCP server.
+**Note:** Kubernetes token-based MCP authorization only works when Lightspeed Core Stack is configured with Kubernetes authentication (`authentication.k8s`). For any other authentication types, MCP servers configured with `Authorization: "kubernetes"` are removed from the available MCP servers list.
 
 ##### 3. Client-Provided Tokens (For Per-User Authentication)
 
@@ -418,6 +419,34 @@ curl -X POST "http://localhost:8080/v1/query" \
 
 **Structure**: `MCP-HEADERS: {"<server-name>": {"<header-name>": "<header-value>", ...}, ...}`
 
+##### Client-Authenticated MCP Servers Discovery
+
+To help clients determine which MCP servers require client-provided tokens, use the **MCP Client Auth Options** endpoint:
+
+```bash
+GET /v1/mcp-auth/client-options
+```
+
+**Response:**
+```json
+{
+  "servers": [
+    {
+      "name": "user-specific-service",
+      "client_auth_headers": ["Authorization", "X-User-Token"]
+    },
+    {
+      "name": "github-integration",
+      "client_auth_headers": ["Authorization"]
+    }
+  ]
+}
+```
+
+This endpoint returns only MCP servers configured with `authorization_headers: "client"`, along with the specific header names that need to be provided via `MCP-HEADERS`. Servers using file-based or Kubernetes authentication are not included in this response.
+
+**Use case:** Clients can call this endpoint at startup or before making requests to discover which servers they can authenticate with using their own tokens.
+
 ##### Combining Authentication Methods
 
 You can mix and match authentication methods across different MCP servers, and even combine multiple methods for a single server:
@@ -698,6 +727,7 @@ options:
   -v, --verbose         make it verbose
   -d, --dump-configuration
                         dump actual configuration into JSON file and quit
+  -s, --dump-schema     dump configuration schema into OpenAPI-compatible file and quit
   -c CONFIG_FILE, --config CONFIG_FILE
                         path to configuration file (default: lightspeed-stack.yaml)
 
@@ -711,14 +741,19 @@ Usage: make <OPTIONS> ... <TARGETS>
 Available targets are:
 
 run                               Run the service locally
+help                              Show this help screen
+run-llama-stack                   Start Llama Stack with enriched config (for local service mode)
 test-unit                         Run the unit tests
 test-integration                  Run integration tests tests
 test-e2e                          Run end to end tests for the service
+test-e2e-local                    Run end to end tests for the service
+benchmarks                        Run benchmarks
 check-types                       Checks type hints in sources
 security-check                    Check the project for security issues
 format                            Format the code into unified format
 schema                            Generate OpenAPI schema file
 openapi-doc                       Generate OpenAPI documentation
+generate-documentation            Generate documentation
 requirements.txt                  Generate requirements.txt file containing hashes for all non-devel packages
 doc                               Generate documentation for developers
 docs/config.puml                  Generate PlantUML class diagram for configuration
@@ -733,7 +768,8 @@ ruff                              Check source code using Ruff linter
 verify                            Run all linters
 distribution-archives             Generate distribution archives to be uploaded into Python registry
 upload-distribution-archives      Upload distribution archives into Python registry
-help                              Show this help screen
+konflux-requirements              generate hermetic requirements.*.txt file for konflux build
+konflux-rpm-lock 	                generate rpm.lock.yaml file for konflux build
 ```
 
 ## Running Linux container image
@@ -1195,7 +1231,10 @@ The script also updates the Tekton pipeline configurations (`.tekton/lightspeed-
 
 ### Updating RPM Dependencies
 
-**Prerequisites:** Install [rpm-lockfile-prototype](https://github.com/konflux-ci/rpm-lockfile-prototype?tab=readme-ov-file#installation)
+**Prerequisites:**
+- Install [rpm-lockfile-prototype](https://github.com/konflux-ci/rpm-lockfile-prototype?tab=readme-ov-file#installation)
+- Have an active RHEL Subscription, get activation keys from [RH console](https://console.redhat.com/insights/connector/activation-keys)
+- Have `dnf` installed in system
 
 **Steps:**
 
@@ -1203,12 +1242,24 @@ The script also updates the Tekton pipeline configurations (`.tekton/lightspeed-
 
 2. **If you changed the base image**, extract its repo file:
 ```shell
+# UBI images
 podman run -it $BASE_IMAGE cat /etc/yum.repos.d/ubi.repo > ubi.repo
+# RHEL images
+podman run -it $BASE_IMAGE cat /etc/yum.repos.d/redhat.repo > redhat.repo
+```
+If the repo file contains too many entries, we can filter them and keep only required repositories.
+Here is the command to check active repositories:
+```shell
+dnf repolist
+```
+Replace the architecture tag (`uname -m`) to `$basearch` so that rpm-lockfile-prototype can replace it with requested architecture names.
+```shell
+sed -i "s/$(uname -m)/\$basearch/g" redhat.repo
 ```
 
-3. **Generate the lock file**:
+1. **Generate the lock file**:
 ```shell
-rpm-lockfile-prototype --image $BASE_IMAGE rpms.in.yaml
+make konflux-rpm-lock
 ```
 
 This creates `rpms.lock.yaml` with pinned RPM versions.

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/pyproject.toml

@@ -24,8 +24,8 @@ dependencies = [
     "fastapi>=0.115.12",
     "uvicorn>=0.34.3",
     "kubernetes>=30.1.0",
-    "llama-stack==0.3.5",
-    "llama-stack-client==0.3.5",
+    "llama-stack==0.4.3",
+    "llama-stack-client==0.4.3",
     "rich>=14.0.0",
     "cachetools>=6.1.0",
     "prometheus-client>=0.22.1",
@@ -47,8 +47,9 @@ dependencies = [
     "einops>=0.8.1",
     "azure-core>=1.38.0",
     "azure-identity",
+    "pyasn1>=0.6.2",
 ]
-version = "0.4.0"
+version = "0.4.1"
 
 [project.license]
 file = "LICENSE"
@@ -64,9 +65,6 @@ Issues = "https://github.com/lightspeed-core/lightspeed-stack/issues"
 exclude = [
     "src/authentication/k8s.py",
     "src/app/endpoints/conversations.py",
-    "src/app/endpoints/query.py",
-    "src/app/endpoints/streaming_query.py",
-    "src/utils/endpoints.py",
 ]
 extraPaths = [
     "./src",
@@ -152,6 +150,7 @@ dev = [
     "bandit>=1.8.6",
     "pybuild-deps>=0.5.0",
     "pip==24.3.1",
+    "pytest-benchmark>=5.2.3",
 ]
 llslibdev = [
     "tree_sitter>=0.24.0",

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/database.py

@@ -19,7 +19,15 @@ session_local: Optional[sessionmaker] = None
 
 
 def get_engine() -> Engine:
-    """Get the database engine. Raises an error if not initialized."""
+    """Get the database engine. Raises an error if not initialized.
+
+    Returns:
+        Engine: The initialized SQLAlchemy Engine instance.
+
+    Raises:
+        RuntimeError: If the database engine has not been initialized; call
+        initialize_database() first.
+    """
     if engine is None:
         raise RuntimeError(
             "Database engine not initialized. Call initialize_database() first."
@@ -28,12 +36,29 @@ def get_engine() -> Engine:
 
 
 def create_tables() -> None:
-    """Create tables."""
+    """Create tables.
+
+    Create all ORM tables defined on Base.metadata using the currently initialized engine.
+
+    Raises:
+        RuntimeError: If the global database engine is not initialized (call
+        initialize_database() first).
+    """
     Base.metadata.create_all(get_engine())
 
 
 def get_session() -> Session:
-    """Get a database session. Raises an error if not initialized."""
+    """Get a database session. Raises an error if not initialized.
+
+    Provide a new ORM Session bound to the configured engine.
+
+    Returns:
+        Session: A SQLAlchemy ORM Session instance bound to the initialized engine.
+
+    Raises:
+        RuntimeError: If the database has not been initialized; call
+        initialize_database() first.
+    """
     if session_local is None:
         raise RuntimeError(
             "Database session not initialized. Call initialize_database() first."
@@ -42,7 +67,20 @@ def get_session() -> Session:
 
 
 def _create_sqlite_engine(config: SQLiteDatabaseConfiguration, **kwargs: Any) -> Engine:
-    """Create SQLite database engine."""
+    """Create SQLite database engine.
+
+    Parameters:
+        config (SQLiteDatabaseConfiguration): Configuration containing
+        `db_path` for the SQLite file.
+        **kwargs: Additional keyword arguments forwarded to SQLAlchemy's create_engine.
+
+    Returns:
+        Engine: A SQLAlchemy Engine bound to the specified SQLite database file.
+
+    Raises:
+        FileNotFoundError: If the parent directory of `config.db_path` does not exist.
+        RuntimeError: If engine creation fails.
+    """
     if not Path(config.db_path).parent.exists():
         raise FileNotFoundError(
             f"SQLite database directory does not exist: {config.db_path}"
@@ -58,7 +96,25 @@ def _create_sqlite_engine(config: SQLiteDatabaseConfiguration, **kwargs: Any) ->
 def _create_postgres_engine(
     config: PostgreSQLDatabaseConfiguration, **kwargs: Any
 ) -> Engine:
-    """Create PostgreSQL database engine."""
+    """Create PostgreSQL database engine.
+
+    Builds a connection URL from the configuration and creates an Engine. If
+    the configuration specifies a non-default namespace (a schema other than
+    "public"), ensures that schema exists by creating it if necessary. If a CA
+    certificate path is provided, the engine will be configured to use it for
+    SSL.
+
+    Parameters:
+        config (PostgreSQLDatabaseConfiguration): Connection and database
+        settings (user, password, host, port, db, ssl/gss options, optional
+        namespace and ca_cert_path).
+
+    Returns:
+        Engine: A SQLAlchemy Engine connected to the configured PostgreSQL database.
+
+    Raises:
+        RuntimeError: If engine creation fails or if creating the specified schema fails.
+    """
     postgres_url = (
         f"postgresql://{config.user}:{config.password.get_secret_value()}@"
         f"{config.host}:{config.port}/{config.db}"
@@ -100,7 +156,18 @@ def _create_postgres_engine(
 
 
 def initialize_database() -> None:
-    """Initialize the database engine."""
+    """Initialize the database engine.
+
+    Initialize module-level database engine and session factory from the
+    application's configuration.
+
+    Reads configuration.database_configuration to determine the database type
+    (SQLite or PostgreSQL), creates and assigns a module-level `engine`, and
+    initializes `session_local` as a sessionmaker bound to that engine. The
+    engine is configured to echo SQL when the logger is at DEBUG level and to
+    use connection pre-ping. May raise RuntimeError if engine creation or
+    required schema creation fails.
+    """
     db_config = configuration.database_configuration
 
     global engine, session_local  # pylint: disable=global-statement

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/README.md

@@ -30,6 +30,9 @@ Handlers for health REST API endpoints.
 ## [info.py](info.py)
 Handler for REST API call to provide info.
 
+## [mcp_auth.py](mcp_auth.py)
+Handler for REST API calls related to MCP server authentication.
+
 ## [metrics.py](metrics.py)
 Handler for REST API call to provide metrics.
 

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/a2a.py

@@ -7,18 +7,17 @@ import uuid
 from datetime import datetime, timezone
 from typing import Annotated, Any, AsyncIterator, MutableMapping, Optional
 
-from fastapi import APIRouter, Depends, HTTPException, Request, status
-from llama_stack.apis.agents.openai_responses import (
-    OpenAIResponseObjectStream,
-)
-from llama_stack_client import APIConnectionError
-from starlette.responses import Response, StreamingResponse
-
+from a2a.server.agent_execution import AgentExecutor, RequestContext
+from a2a.server.apps import A2AStarletteApplication
+from a2a.server.events import EventQueue
+from a2a.server.request_handlers import DefaultRequestHandler
+from a2a.server.tasks import TaskStore
+from a2a.server.tasks.task_updater import TaskUpdater
 from a2a.types import (
+    AgentCapabilities,
     AgentCard,
-    AgentSkill,
     AgentProvider,
-    AgentCapabilities,
+    AgentSkill,
     Artifact,
     Message,
     Part,
@@ -28,27 +27,27 @@ from a2a.types import (
     TaskStatusUpdateEvent,
     TextPart,
 )
-from a2a.server.agent_execution import AgentExecutor, RequestContext
-from a2a.server.events import EventQueue
-from a2a.server.request_handlers import DefaultRequestHandler
-from a2a.server.tasks import TaskStore
-from a2a.server.tasks.task_updater import TaskUpdater
-from a2a.server.apps import A2AStarletteApplication
 from a2a.utils import new_agent_text_message, new_task
+from fastapi import APIRouter, Depends, HTTPException, Request, status
+from llama_stack_api.openai_responses import (
+    OpenAIResponseObjectStream,
+)
+from llama_stack_client import APIConnectionError
+from starlette.responses import Response, StreamingResponse
 
-from authentication.interface import AuthTuple
-from authentication import get_auth_dependency
-from authorization.middleware import authorize
-from configuration import configuration
-from a2a_storage import A2AStorageFactory, A2AContextStore
-from models.config import Action
-from models.requests import QueryRequest
+from a2a_storage import A2AContextStore, A2AStorageFactory
 from app.endpoints.query import (
-    select_model_and_provider_id,
     evaluate_model_hints,
+    select_model_and_provider_id,
 )
 from app.endpoints.streaming_query_v2 import retrieve_response
+from authentication import get_auth_dependency
+from authentication.interface import AuthTuple
+from authorization.middleware import authorize
 from client import AsyncLlamaStackClientHolder
+from configuration import configuration
+from models.config import Action
+from models.requests import QueryRequest
 from utils.mcp_headers import mcp_headers_dependency
 from utils.responses import extract_text_from_response_output_item
 from version import __version__

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/authorized.py

@@ -31,6 +31,8 @@ async def authorized_endpoint_handler(
     Process POST requests to the /authorized endpoint, returning
     the authenticated user's ID and username.
 
+    The response intentionally omits any authentication token.
+
     Returns:
         AuthorizedResponse: Contains the user ID and username of the authenticated user.
     """

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/config.py

@@ -44,6 +44,8 @@ async def config_endpoint_handler(
     Process GET requests to the /config endpoint and returns the
     current service configuration.
 
+    Ensures the application configuration is loaded before returning it.
+
     Returns:
         ConfigurationResponse: The loaded service configuration response.
     """

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/conversations_v3.py

@@ -7,7 +7,6 @@ from fastapi import APIRouter, Depends, HTTPException, Request, status
 from llama_stack_client import (
     APIConnectionError,
     APIStatusError,
-    NOT_GIVEN,
 )
 from sqlalchemy.exc import SQLAlchemyError
 
@@ -332,10 +331,10 @@ async def get_conversation_endpoint_handler(
         # Use Conversations API to retrieve conversation items
         conversation_items_response = await client.conversations.items.list(
             conversation_id=llama_stack_conv_id,
-            after=NOT_GIVEN,
-            include=NOT_GIVEN,
-            limit=NOT_GIVEN,
-            order=NOT_GIVEN,
+            after=None,
+            include=None,
+            limit=None,
+            order=None,
         )
         items = (
             conversation_items_response.data

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/feedback.py

@@ -151,6 +151,9 @@ def store_feedback(user_id: str, feedback: dict) -> None:
     Parameters:
         user_id (str): Unique identifier of the user submitting feedback.
         feedback (dict): Feedback data to be stored, merged with user ID and timestamp.
+
+    Raises:
+        HTTPException: If writing the feedback file fails (HTTP 500).
     """
     logger.debug("Storing feedback for user %s", user_id)
     # Creates storage path only if it doesn't exist. The `exist_ok=True` prevents

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/health.py

@@ -6,10 +6,10 @@ methods. For HEAD HTTP method, just the HTTP response code is used.
 """
 
 import logging
+from enum import Enum
 from typing import Annotated, Any
 
 from fastapi import APIRouter, Depends, Response, status
-from llama_stack.providers.datatypes import HealthStatus
 from llama_stack_client import APIConnectionError
 
 from authentication import get_auth_dependency
@@ -30,6 +30,18 @@ logger = logging.getLogger("app.endpoints.handlers")
 router = APIRouter(tags=["health"])
 
 
+# HealthStatus enum was removed from llama_stack in newer versions
+# Defining locally for compatibility
+class HealthStatus(str, Enum):
+    """Health status enum for provider health checks."""
+
+    OK = "ok"
+    ERROR = "Error"
+    NOT_IMPLEMENTED = "not_implemented"
+    HEALTHY = "healthy"
+    UNKNOWN = "unknown"
+
+
 get_readiness_responses: dict[int | str, dict[str, Any]] = {
     200: ReadinessResponse.openapi_response(),
     401: UnauthorizedResponse.openapi_response(
@@ -96,6 +108,11 @@ async def readiness_probe_get_method(
     If any provider reports an error status, responds with HTTP 503
     and details of unhealthy providers; otherwise, indicates the
     service is ready.
+
+    Returns:
+        ReadinessResponse: Object with `ready` indicating overall readiness,
+        `reason` explaining the outcome, and `providers` containing the list of
+        unhealthy ProviderHealthStatus entries (empty when ready).
     """
     # Used only for authorization
     _ = auth

{lightspeed_stack-0.4.0 → lightspeed_stack-0.4.1}/src/app/endpoints/info.py

@@ -44,6 +44,12 @@ async def info_endpoint_handler(
     Process GET requests to the /info endpoint, returning the
     service name, version and Llama-stack version.
 
+    Raises:
+        HTTPException: with status 500 and a detail object
+        containing `response` and `cause` when unable to connect to
+        Llama Stack. It can also return status 401 or 403 for
+        unauthorized access.
+
     Returns:
         InfoResponse: An object containing the service's name and version.
     """